import pandas as pd
import seaborn as sns
import plotly.express as px
import numpy as np

import matplotlib.pyplot as plt
import matplotlib.dates as mdates

import plotly.io as pio
pio.renderers.default = "plotly_mimetype+notebook"

Matplotlib

For this excercise, we have written the following code to load the stock dataset built into plotly express.

stocks = px.data.stocks()
#stocks.set_index('date', inplace = True)
stocks.head()

	date	GOOG	AAPL	AMZN	FB	NFLX	MSFT
0	2018-01-01	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	2018-01-08	1.018172	1.011943	1.061881	0.959968	1.053526	1.015988
2	2018-01-15	1.032008	1.019771	1.053240	0.970243	1.049860	1.020524
3	2018-01-22	1.066783	0.980057	1.140676	1.016858	1.307681	1.066561
4	2018-01-29	1.008773	0.917143	1.163374	1.018357	1.273537	1.040708

Question 1:

Select a stock and create a suitable plot for it. Make sure the plot is readable with relevant information, such as date, values.

# YOUR CODE HERE
# Select data
x = stocks.date
y = stocks.GOOG

# Set the figure size
plt.rcParams["figure.figsize"] = [12.00, 12.00]
plt.rcParams["figure.autolayout"] = True

# Set subplot
fig, ax = plt.subplots()
ax.plot(x,y)
# set title
ax.set_title('Google stock')
# horizontal axis
ax.set_xlabel('Date')
# vertical axis
ax.set_ylabel('stock value')

# Select number of ticks
ticks = list(stocks['date'])
plt.xticks([ticks[i] for i in range(len(ticks)) if i % 10 == 0], rotation = 'horizontal')

plt.show()

Question 2:

You've already plot data from one stock. It is possible to plot multiples of them to support comparison.
To highlight different lines, customise line styles, markers, colors and include a legend to the plot.

# YOUR CODE HERE
# Select data
x = stocks.date
y = stocks.GOOG
y2 = stocks.AAPL
y3 = stocks.AMZN
y4 = stocks.FB
y5 = stocks.NFLX
y6 = stocks.MSFT

# Set the figure size
plt.rcParams["figure.figsize"] = [12.00, 12.00]
plt.rcParams["figure.autolayout"] = True

# Set subplot
fig, ax = plt.subplots()

# Plot data
ax.plot(x,y, label = 'GOOG')
ax.plot(x, y2, label = 'AAPL')
ax.plot(x, y3, label = 'AMZN')
ax.plot(x, y4, label = 'FB')
ax.plot(x, y5, label = 'NFLX')
ax.plot(x, y6, label = 'MSFT')

# set title
ax.set_title('Stocks')
# horizontal axis
ax.set_xlabel('Date')
# vertical axis
ax.set_ylabel('stock value')

# Legend
ax.legend(loc=0)

# Select number of ticks
ticks = list(stocks['date'])
plt.xticks([ticks[i] for i in range(len(ticks)) if i % 10 == 0], rotation = 'horizontal')

plt.show()

Seaborn

First, load the tips dataset

tips = sns.load_dataset('tips')
# Add column with tipping percentage to dataframe 
tips['tip_percentage'] = tips.tip / tips.total_bill
tips.head()

	total_bill	tip	sex	smoker	day	time	size	tip_percentage
0	16.99	1.01	Female	No	Sun	Dinner	2	0.059447
1	10.34	1.66	Male	No	Sun	Dinner	3	0.160542
2	21.01	3.50	Male	No	Sun	Dinner	3	0.166587
3	23.68	3.31	Male	No	Sun	Dinner	2	0.139780
4	24.59	3.61	Female	No	Sun	Dinner	4	0.146808

Question 3:

Let's explore this dataset. Pose a question and create a plot that support drawing answers for your question.

Some possible questions:

• Are there differences between male and female when it comes to giving tips?
• What attribute correlate the most with tip?

# YOUR CODE HERE
# Are there differences between male and female when it comes to giving tips?

# Set the figure size
plt.rcParams["figure.figsize"] = [12.00, 5]
plt.rcParams["figure.autolayout"] = True

#sns.scatterplot(x='total_bill', y='tip', hue = 'sex', data=tips)

sns.boxplot(x='sex', y='tip_percentage', data=tips)
plt.show()

Plotly Express

Question 4:

Redo the above exercises (challenges 2 & 3) with plotly express. Create diagrams which you can interact with.

The stocks dataset

Hints:

• Turn stocks dataframe into a structure that can be picked up easily with plotly express

stocks = px.data.stocks()
#stocks.set_index('date', inplace = True)
stocks.head()

	date	GOOG	AAPL	AMZN	FB	NFLX	MSFT
0	2018-01-01	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	2018-01-08	1.018172	1.011943	1.061881	0.959968	1.053526	1.015988
2	2018-01-15	1.032008	1.019771	1.053240	0.970243	1.049860	1.020524
3	2018-01-22	1.066783	0.980057	1.140676	1.016858	1.307681	1.066561
4	2018-01-29	1.008773	0.917143	1.163374	1.018357	1.273537	1.040708

# YOUR CODE HERE
fig = px.line(stocks, x='date', y=stocks.columns[1:], markers = True)
fig.update_layout(legend=dict(
    title="Stocks"
))
fig.show()

The tips dataset

# YOUR CODE HERE
df = tips
fig = px.box(df, x = 'sex', y = 'tip_percentage')
fig.show()

Question 5:

Recreate the barplot below that shows the population of different continents for the year 2007.

Hints:

• Extract the 2007 year data from the dataframe. You have to process the data accordingly
• use plotly bar
• Add different colors for different continents
• Sort the order of the continent for the visualisation. Use axis layout setting
• Add text to each bar that represents the population

#load data
df = px.data.gapminder()
df.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

# YOUR CODE HERE
df_2007 = df.query('year==2007')
df_2007_new = df_2007.groupby('continent').sum()
df_2007_new = df_2007_new.reset_index()

fig = px.bar(df_2007_new, y="continent", x="pop", color="continent", orientation="h", hover_name = 'pop', text = 'pop',
             color_discrete_map={
                "Europe": "red",
                "Asia": "green",
                "Americas": "blue",
                "Oceania": "goldenrod",
                "Africa": "magenta"},
             category_orders={"continent": ["Asia", "Africa", "Americas", "Europe", "Oceania"]},
             title="Question 5"
            )

fig.show()